Wyniki wyszukiwania - BazTech

1

Video-based HR measurement using adaptive facial regions with multiple color spaces

Panigrahi Arpita, Sharma Hemant, Mukherjee Atin

Biocybernetics and Biomedical Engineering

|

2024

|

Vol. 44, no. 1

68--82

EN

Driven by the desire for feasible and convenient healthcare, non-contact heart rate (HR) monitoring based on consumer-grade cameras has gained significant recognition among researchers. However, this technology suffers from performance reliability and consistency in realistic situations of motion artifacts, illumination variations, and skin tones, limiting it to emerge as an alternative to conventional methods. Considering these challenges, this paper suggests an effective technique for HR measurement from facial RGB videos. The face being the region of interest (ROI) is divided into several small sub-ROIs of even size. A group of quality sub-ROIs is formed and weighted based on the fundamental periodicity coefficient to handle spatial non-uniform illumination and facial motions. Five different color spaces are considered, and the most suitable color component from each space is chosen to alleviate the influence of temporal illumination variation and other factors. The resultant color signals are denoised using the ensemble empirical mode decomposition and integrated using the principal component analysis to derive a pulsating component representing the blood volumetric changes for HR computation. Experiments are conducted over three standard datasets, namely PURE, UBFC, and COHFACE. The obtained mean absolute error values are 1.16 beats per minute (bpm), 1.56 bpm, and 2.10 bpm for PURE, UBFC, and COHFACE datasets, respectively, indicating the performance of the technique well above the clinically acceptable threshold. In comparison, the technique showed performance superiority over the state-of-art methods. These outcomes substantiate the potential of alternative color spaces for accurate and reliable HR monitoring from facial videos in challenging scenarios.

2

Ocena zmienności rytmu serca pod wpływem muzyki na podstawie sygnału fotopletyzmograficznego

Wilk B., Post P.

Przegląd Elektrotechniczny

|

2018

|

R. 94, nr 8

150--153

PL

W artykule opisano algorytm opracowany do wyznaczania zmienności rytmu serca (tzw. sygnału HRV) na podstawie wartości chwilowych okresu sygnału PPG, który reprezentuje falę tętna obwodowego. Sygnał PPG został zarejestrowany podczas oddziaływania muzyki. Do wydzielenia składowych sygnału HRV (tj. fluktuacji i nieliniowego trendu) zastosowano dyskretną transformatę falkową. Do oceny wpływu muzyki na częstość pracy serca przyjęto parametry opisujące zarówno zmienność fluktuacji rytmu serca, jak i wolnozmiennego trendu.

EN

In this article, the algorithm developed for determination of HRV based on the PPG signal representing the peripheral pulse wave was described. The PPG signal was recorded under the influence of music. The components of HRV signal (i.e. a nonlinear trend and fluctuations) were extracted by using the DWT. The parameters representing variability of the HRV fluctuations as well as trend were applied to assessment of HRV.

3

Wyznaczanie częstości oddychania na podstawie analizy widmowej zmienności okresu sygnału fotopletyzmograficznego

Wilk B., Pazowski M.

Pomiary Automatyka Kontrola

|

2014

|

R. 60, nr 8

610--613

PL

W artykule opisano algorytm do wyznaczania częstości oddychania na podstawie analizy widmowej sygnału reprezentującego zmienność okresu fali tętna. Falę tętna zarejestrowano za pomocą czujnika fotopletyzmograficznego (tzw. PPG) umieszczonego na placu ręki. Do przetwarzania sygnału PPG zaproponowano zastosowanie analizy falkowej. Przeprowadzono także ocenę dokładności opracowanej metody wykorzystując sygnał referencyjny, który reprezentuje przepływ powietrza w czasie wydechu.

EN

The arterial pressure waveform contains valuable information regarding the respiratory rate. This paper describes the algorithm developed for estimating the respiratory rate by analyzing the period variability of the peripheral pulse wave. To record a pulse wave at the finger, a transmissiontype photoplethysmographic sensor was used. PPG signals were collected from 10 healthy subjects during free breathing, and breath holding over a period of 3-min using a data acquisition system (Fig. 1). The reference breathing rate was determined from the airflow signal recorded simultaneously with the PPG signal (Figs. 7 and 8). Firstly, the PPG signal was detrended and denoised using the wavelet transform (Fig. 2 and 3). Based on the locations of the maximum points, all periods were detected and the tachogram was constructed. The signal representing the period variability (PPV) was obtained by interpolating the envelope of the tachogram with a cubic polynomial function (Fig. 5). Then, fluctuations extracted by the DWT from the PPV signal were segmented into 10 s intervals. Using Burg’s method, the AR model based PSD was computed for each segment. Finally, the respiratory component was detected as the maximum in the frequency band of 0.150.4 Hz (Fig. 6). The obtained results show (Fig. 9) that the proposed method allows us to monitor the respiratory rate and to detect the induced apnea with the acceptable accuracy.

4

Wyznaczanie częstości oddychania na podstawie analizy obwiedni amplitudowej sygnału PPG

Wilk B.

Pomiary Automatyka Kontrola

|

2013

|

R. 59, nr 12

1298--1300

PL

W artykule przedstawiono metodę wyznaczania częstości oddychania na podstawie analizy górnej obwiedni amplitudowej sygnału PPG, który reprezentuje falę tętna obwodowego w palcu ręki. Obwiednię uzyskano w wyniku aproksymacji lokalnych maksimów splajnami. Opracowana metoda umożliwia określenie czasu trwania każdego cyklu oddechowego oraz pozwala wykryć bezdech. Do oceny dokładności tej metody wykorzystano sygnał referencyjny, który reprezentuje przepływ powietrza w czasie oddychania.

EN

This paper presents a novel method for the estimation of respiratory rate by analyzing the amplitude envelope of a peripheral pulse wave. To record a pulse wave at the finger of the hand a transmission-type photoplethysmographic (PPG) sensor was used. The PPG sensor is sensitive to variations in blood volume. Variations in blood volume are caused by cardiovascular regulation, thermoregulation and respiration. PPG signals show significant morphological differences under the normal and induced apnea conditions (Fig.2). The amplitude fluctuations of PPG were found to drop under apnea (Fig.3).The amplitude envelope of the PPG signal was obtained by interpolating every interval [maxi, maxi + 1] with a cubic polynomial function (Figs. 1 and 3). The breathing rate determined from the airflow signal recorded simultaneously with the PPG signal, served as a reference value (Fig. 5). The results show that the proposed method is a promising technique for detection of each respiratory period, for calculating a respiratory rate, and for detecting apnea (Fig. 5, Fig. 7).

5

Ocena sztywności tętnic na podstawie analizy falkowej sygnału fotopletyzmograficznego

Wilk B., Marek W.

Pomiary Automatyka Kontrola

|

2013

|

R. 59, nr 12

1301--1303

PL

W artykule opisano wirtualny przyrząd opracowany do oceny sztywności ścian dużych tętnic na podstawie analizy sygnału PPG reprezentującego falę tętna obwodowego. Na podstawie lokalizacji charakterystycznych punktów fali tętna są wyznaczane wartości parametrów stosowanych do oceny sztywności tętnic: CT, PPT, RI, SI, IWD. Do detekcji wcięcia dykrotycznego wykorzystano rozwinięcie falkowe uzyskane za pomocą CWT. Trend sygnału PPG wydzielono na podstawie dekompozycji sygnału wg algorytmu Mallata.

EN

Arterial stiffness is recognized as a major determinant of cardiovascular risk. The arterial pressure waveform contains valuable information indicative of both aortic and systemic arterial stiffness. This paper describes a virtual instrument for assessment of arterial stiffness by analyzing the peripheral pulse waveform. The developed software (in LabVIEW) consists of a program for data acquisition and a program for peripheral pulse wave analysis. To record a peripheral pulse wave at a finger, a transmission-type photoplethysmographic (PPG) sensor was used. The PPG sensor is sensitive to variations in the blood volume. The PPG signal was amplified, acquired using a data acquisition system, and stored. Digital signal processing was then performed. Firstly, a non-linear trend and noise were removed from the PPG signal using the DWT (Fig. 1). Then the characteristic points of the pulse wave were detected using a peak detector (Fig. 2). For identification of an invisible dicrotic notch the CWT was successfully employed (Fig. 4). All the detected peaks were verified using the refractory period as a criterion for false detection. Based on the location of the characteristic points of the pulse wave, several parameters including CT, PPT, SI, RI, IWD were calculated to quantify the arterial stiffness (Tab. 1). This study proposes a simple and effective non-invasive method for assessing arterial stiffness to identify individuals with cardiovascular risk earlier and treat them preventively.